Multiple Object Tracking (MOT) has been a useful yet challenging task in many real-world applications such as video surveillance, intelligent retail, and smart city. The challenge is how to model long-term temporal dependencies in an efficient manner. Some recent works employ Recurrent Neural Networks (RNN) to obtain good performance, which, however, requires a large amount of training data. In this paper, we proposed a novel tracking method that integrates the auto-tuning Kalman method for prediction and the Gated Recurrent Unit (GRU) and achieves a near-optimum with a small amount of training data. Experimental results show that our new algorithm can achieve competitive performance on the challenging MOT benchmark, and faster and more robust than the state-of-the-art RNN-based online MOT algorithms.
@article{arxiv.2012.14314,
title = {GAKP: GRU Association and Kalman Prediction for Multiple Object Tracking},
author = {Zhen Li and Sunzeng Cai and Xiaoyi Wang and Zhe Liu and Nian Xue},
journal= {arXiv preprint arXiv:2012.14314},
year = {2020}
}